Gemini 3 Pro
gemini-3-proPricing
List prices at Replicate, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.00 | $12.00 | |
| Prompts over 200K tokens | $4.00 | $18.00 |
What it costs a month
At Replicate list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$1,500
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,392
- Coding agent1,000 requests a day, 40K in / 2K out$3,120
- Overnight batch20,000 requests a day, 4K in / 0.4K out$7,680
Where to run it
2 hosts serve Gemini 3 Pro. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
ReplicateInference gemini-3-pro | $2.00 / $12.00 | gemini-3-pro | |
DatabricksCloud databricks-gemini-3-pro | $2.50 / $15.00 +25% vs headline | databricks-gemini-3-pro |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImagesAudioVideo
- Produces
- Text
- Features
- Audio inputVideo input
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Replicate.
Smaller Google models
- 11% less
- 11% less
- 25% less
Other frontier labs
- 11% less
- 11% less
- 33% less
- 56% less
Open-weight picks
- 3% less
- 11% less
- 52% less
- 56% less
Model line
Newer and older versions, at each lab's own price.
- UndatedGemini 3.1 ProLatest$2.00 / $12.00
- UndatedGemini 3 ProThis page$2.00 / $12.00
- Jun 2025Gemini 2.5 Pro$1.25 / $10.00
Call it
Using Replicate's API.
from litellm import completion
response = completion(
model="replicate/gemini-3-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Gemini 3 Pro cost?
On Replicate, Gemini 3 Pro costs $2.00 per million input tokens and $12.00 per million output tokens.
Which APIs offer Gemini 3 Pro?
Gemini 3 Pro runs on 2 APIs: Replicate and Databricks.
What is Gemini 3 Pro's context window?
1M tokens, with up to 66K tokens in one reply.
Is Gemini 3 Pro being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Gemini 3 Pro?
Yes. Gemini 3.1 Pro is the newest model in this line.
What are cheaper alternatives to Gemini 3 Pro?
Models that cost less and keep most of what it can do: Gemini 4 Carbon on Google AI Studio (11% less), GPT-6.2 Sol on OpenAI (11% less), Claude Sonnet 5.5 on Anthropic (11% less) and Command A Plus on AIHubMix (3% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Gemini 3 Pro's API model id?
Use gemini-3-pro with Replicate. Other hosts use their own ids: databricks-gemini-3-pro on Databricks.
Sources
Raw catalog entry for gemini-3-pro on Replicate
{
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000012,
"litellm_provider": "replicate",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": true,
"supports_system_messages": true,
"supports_tool_choice": false,
"supports_response_schema": false,
"input_cost_per_token_above_200k_tokens": 0.000004,
"output_cost_per_token_above_200k_tokens": 0.000018,
"source": "https://replicate.com/google/gemini-3-pro",
"supports_audio_input": true,
"supports_reasoning": true,
"supports_video_input": true
}